How I art: A beginners guide

A step-by-step guide on how to not generate like the average CivitAI user.

Prettly please; never ever do this.

Warning: This guide is based on SDXL, if you use 1.5, FLUX, etc., this won't be a 1:1, results will vary.

Step 1. Don't use Pony.

For real tho, don't do it.

Step 2. The settings.

Each model comes with its "best" settings, usually attached to the description if the uploader has over 2 braincells or is not the anti-christ.

ChromaXL for example, is nice and based. It tells you the average settings. If this is your first time; go to the middle:
10 steps
2 CFG
Euler A Beta
But if you want to test, Down the line I will explain how to test these configurations.

A rule of thumb is:
The more steps, the less noise. Too many steps and the image changes completely.
The more CFG the more it follows the prompt, less CFG the more creative. But also; higher CFG ups the saturation, while lower CFG washes up the colours.

If you use the in-site generator, it will look something like this:

As you can see, I loaded the model, my LoRA, set a resolution, set the recommended settings and added an upscaler.

Always, and I mean ALWAYS remove the LoRAs you are not going to use, if you upload that image, it will appear on that LoRA's gallery and will negatively impact the betting process of other users when looking for working models. It also makes you look like a clown.

NOTE: Only upscale images you are happy with, upscaling every image will result in a waste of time and credits. More information later. In this guide I will turn it off, then on when needed.

Step 2: The resolution.

The resolution here will be 1024* But depending on what you are generating, a different resolution is recommended.
Portrait works great for full-lenght, Landscape works best for lying down, wide shots, etc. Square for icons and headshot/bust portraits. So on and so forth, your resolution will affect the resulting image. We will do a profile icon for the sake of visual context. If you generate locally on your own equipment like I do, you will be limited by the amount of VRAM you have available.
Further information will be given on a different Article.

Step 3: The positive prompt.

Quality tags:These cange depending on the model, model providers usually give you examples of these tags in the description.
99% of the time these are snake oil, but I use them anyways.
For Noob based models such as Chroma, these tags are:

masterpiece, best quality, newest, absurdres, highres 

I recommend using them like this:

masterpiece, best quality, newest, absurdres, highres, {prompt}, masterpiece, best quality, newest, absurdres, highres

As you can imagine, {prompt} is then replaced by your prompt per se. An example would be:

masterpiece, best quality, newest, absurdres, highres, solo, awff, male, wolf, anthro, bust portrait, smile, clothed, safe, masterpiece, best quality, newest, absurdres, highres

This is, by the way, your POSITIVE prompt. This is what you want on your image.

Now let's break down this simple prompt:

Quality tags: These make sure the model gives out the best looking results possible. Mostly useless but worth using for newbies.

'awff': This is an activation tag, awff does not mean anything, but I used it as keyword for my fursona; meaning that if I load my fursona's LoRA, my character will only appear if I use this tag.

'solo, male, wolf, anthro, bust portrait, smile, clothed, safe': Context tags; this will guide the model to our desired result. Depending on the model; which tags you must use. ChromaXL, KiwiMix, Noob, etc. are trained on Danbooru and e621 tags, meaning that even though their CLIP (won't explain it here) still knows natural language such as "a dog jumping around", it will understand "dog, solo, jumping, outside" a little better.

For example; if your model is trained only on e621 tags, using things like "shiny skin" won't do anything but give the character some glitter around him. Instead use "glistening body".
Shiny skin CAN work, but due to the model bias, results will be at random, while glistening body will land more often on your desired results.

Things to avoid:

1.Repetitive tags; if you tagged "excessive cum, vaginal penetration", you don't need "cum inside". Just by having the penis inside, the model knows the excessive cum goes there. Same with "cum, ejaculation, cum in pussy".

2.Un-related tags; As mentioned earlier, the more you stay true to the training data, the better results you will get. "A very sexy female wolf adult with huge tits" wastes a lot of tokens; just say "solo, female, wolf, huge breasts".

3.Token overflow; Tensor doesn't show this, but prompts work on a 75 token basis. Staying under this limit gives the best results. You can still overflow this and jump to 150, 225, 300, etc. But if one of your tags overflows it, that tag is effectively useless.

Let's say the tag "huge breasts" perfectly divides as "huge" and "breasts", one ending the first 75 tokens and the latter starting the next 75. The model will then barely listen to "huge" and try to re-focus on "breasts". This is fixed with BREAK a syntax that will force the text encoder (not explaining it here) to refresh its attention and giving you a fresh set of tokens. This also is crucial for working with Regional Prompter for those using a WebUI.

4.Syntax clutter; Soon you will learn more about syntax, for now just dont [[((((huge breasts:1.5))))]] or I will hunt you down.

Step 4: The negative prompt.

Don't you touch this. SDXL has one great feature where it almost never needs a negative prompt, even then, at most use the model's recommended negatives such as:

worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands

Only add negatives if the image keeps doing something you don't like. For example, if you want "4 fingers" but it keeps doing 5, then add "5 fingers" to the negatives. If the hair is the wrong colour, or wrong lenght, etc., then negatives are valid, but only then. For this test I won't use negatives.

Things to avoid:

1.Using negatives; just don't.

Step 4.1: Additional settings and options.

This can be skipped if you already feel overstimulated, but I will touch on it pretty quick.

Tensor.art and local generators such as A1111 let you add things to your workflow like "controlnet", "embeddings", etc. Only use these if you know how to use them and how they work. I will drop another guide later on for each tool.

Step 5: Generate!

Now we click generate:

What a nice generation uh? Now let's turn on the upscaler and add our seed to the settings:

Setting a seed (assuming you didn't change the prompt) forces the model to generate the same image over and over. This is great for breaking down prompts from other directors, but is also great for upscaling!

Because ChromaXL is a lighting model, we want our "upscaling steps" to be low, usually half the normal step count, so for 10; I use 5. Furthermore, "Denoising" has to be low as well; If you only want details added go for 0.10 or 0.15; 0.2 to 0.3 will start to alter the image and +0.4 can potentially destroy it.

Lastly, the Upscaler itself; I recommend R-ESRGAN 4x+ Anime6B, but if you use a local generator I then suggest getting a custom one such as 4xUltrasharp_4xUltrasharpV10

Now that we have the seed set and the upscaler configurated, generate again!

As you can see, the difference is minimal, but the added resolution and low denoise make sure the small details pop and the artifacts get solved. In this case it went from 1024* to 1200* so it also makes the image less pixelated if seen at higher-res monitors. It also makes for a more detailed image if compressed; aka you posted it on Twitter.

And that's it!

Congratulations, now you know the basics of AI generation on XL models. Remember to always do research on the model and LoRAs you are going to use, chances are the creator added some tasty instructions under the Description and your lazy ass didn't read them. HAVE FUN!